works on

From the 2 of 15 linked papers with an AI index.

activity
20242026
collaborators

14 papers

astro-ph.HE2026

Observation of A Solar Like Magnetic Reconnection Event in an AGN Corona with XRISM

Gal Vardi, Ehud Behar, Liyi Gu +14

The authors present the first direct observation of a magnetic reconnection flare in the X‑ray corona of the active galaxy NGC 3783, using XRISM and XMM‑Newton data that reveal a N…

cs.LG2026

To Grok Grokking: Provable Grokking in Ridge Regression

Mingyue Xu, Gal Vardi, Itay Safran

The paper provides a theoretical analysis of grokting—delayed generalization after overfitting—in ridge regression, showing how gradient descent with weight decay leads to three ph…

cs.LG2026

The Implicit Bias of Adam and Muon on Smooth Homogeneous Neural Networks

Eitan Gronich, Gal Vardi

We study the implicit bias of momentum-based optimizers on smooth homogeneous models. We show that \textit{momentum steepest descent} algorithms like Muon (spectral norm), Momentum…

cs.LG2026

Learning to Think from Multiple Thinkers

Nirmit Joshi, Roey Magen, Nathan Srebro +2

We study learning with Chain-of-Thought (CoT) supervision from multiple thinkers, all of whom provide correct but possibly systematically different solutions, e.g., step-by-step so…

cs.LG2026

ImpMIA: Leveraging Implicit Bias for Membership Inference Attack

Yuval Golbari, Navve Wasserman, Gal Vardi +1

Determining which data samples were used to train a model, known as Membership Inference Attack (MIA), is a well-studied and important problem with implications on data privacy. So…

cs.LG2026

Positive Distribution Shift as a Framework for Understanding Tractable Learning

Marko Medvedev, Idan Attias, Elisabetta Cornacchia +3

We study a setting where the goal is to learn a target function f(x) with respect to a target distribution D(x), but training is done on i.i.d. samples from a different training di…